Elephant MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Pino log level (error, warn, info, debug). | info |
| AWS_REGION | No | AWS region for Bedrock API calls. | us-east-1 |
| OPENAI_API_KEY | No | OpenAI API key for embeddings. When set, OpenAI is used; otherwise falls back to AWS Bedrock. | |
| ORACLE_GEO_INDEX_CID | No | Fixed CID of the derived geo/value index; used when ORACLE_GEO_INDEX_IPNS is unset. | |
| ORACLE_GEO_INDEX_IPNS | No | IPNS name of the derived geo/value index (e.g. oracle-geo-index-lee); resolved to its current CID at runtime. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| listClassesByDataGroupA | List lexicon classes in one Elephant data group. |
| listPropertiesByClassNameB | List non-deprecated lexicon properties for one class. |
| getPropertySchemaB | Return the lexicon schema for one class property. |
| getVerifiedScriptExamplesA | Search verified Elephant transform scripts semantically. |
| listAtlasCountiesA | List the synchronized counties, their data groups, and publication CIDs. |
| listAtlasPropertiesB | List the property CIDs and data-group roots of one state/county/data group. |
| getAtlasPropertyB | Assemble one property: its roots, class rows, relationship rows, and the entities they reach. |
| getAtlasDatasetInfoB | Return the row count of every table in one state/county/data group and its publication CIDs. |
| queryAtlasA | Run one read-only SELECT over the synchronized tables of one state/county/data group. Table names are those from getAtlasSchema (property, address, properties, ...). |
| getAtlasSchemaA | List the tables of one state/county/data group, or the columns of one table, for queryAtlas. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool serves a distinct purpose: listing vs. getting specific Atlas properties, dataset info, schema access, lexicon queries, and script search. There is no overlap or ambiguity between the tools.
All tool names follow a consistent camelCase verb_noun pattern (list, get, query) with clear resource nouns, making it easy to predict behavior from names.
The 10 tools cover the read-only data access and lexicon schema domain without redundancy. The count is well within the ideal range for a focused server.
The surface covers the core workflows: listing datasets/counties, inspecting schemas, running queries, and retrieving lexicon details. The read-only nature is clearly communicated, and no critical operations are missing for the apparent purpose.